!pip install plotly

Requirement already satisfied: plotly in c:\users\user\anaconda3\lib\site-packages (5.10.0)
Requirement already satisfied: tenacity>=6.2.0 in c:\users\user\anaconda3\lib\site-packages (from plotly) (8.0.1)

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px

path="C:\\Users\\user\\ict_class\\kaggle4th_flask_ml\\wine_flask_test\\"
df = pd.read_csv(path + "data\wine.csv")

df

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality	Id
0	7.4	0.700	0.00	1.9	0.076	11.0	34.0	0.99780	3.51	0.56	9.4	5	0
1	7.8	0.880	0.00	2.6	0.098	25.0	67.0	0.99680	3.20	0.68	9.8	5	1
2	7.8	0.760	0.04	2.3	0.092	15.0	54.0	0.99700	3.26	0.65	9.8	5	2
3	11.2	0.280	0.56	1.9	0.075	17.0	60.0	0.99800	3.16	0.58	9.8	6	3
4	7.4	0.700	0.00	1.9	0.076	11.0	34.0	0.99780	3.51	0.56	9.4	5	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...
1138	6.3	0.510	0.13	2.3	0.076	29.0	40.0	0.99574	3.42	0.75	11.0	6	1592
1139	6.8	0.620	0.08	1.9	0.068	28.0	38.0	0.99651	3.42	0.82	9.5	6	1593
1140	6.2	0.600	0.08	2.0	0.090	32.0	44.0	0.99490	3.45	0.58	10.5	5	1594
1141	5.9	0.550	0.10	2.2	0.062	39.0	51.0	0.99512	3.52	0.76	11.2	6	1595
1142	5.9	0.645	0.12	2.0	0.075	32.0	44.0	0.99547	3.57	0.71	10.2	5	1597

1143 rows × 13 columns

column 명	뜻
fixed acidity	고정산
volatile acidity	휘발성 산
citric acid	구연산
residual sugar	잔당
chlorides	염화물
free sulfur dioxide	자유 이산화황
total sulfur dioxide	전체 이산화황
density	밀도
pH	산도
sulphates	황산염
alcohol	알코올
quality (score between 0 and 10)	품질

열(column)별 통계

df.describe()[1:].T.style.background_gradient(cmap='Reds')

	mean	std	min	25%	50%	75%	max
fixed acidity	8.311111	1.747595	4.600000	7.100000	7.900000	9.100000	15.900000
volatile acidity	0.531339	0.179633	0.120000	0.392500	0.520000	0.640000	1.580000
citric acid	0.268364	0.196686	0.000000	0.090000	0.250000	0.420000	1.000000
residual sugar	2.532152	1.355917	0.900000	1.900000	2.200000	2.600000	15.500000
chlorides	0.086933	0.047267	0.012000	0.070000	0.079000	0.090000	0.611000
free sulfur dioxide	15.615486	10.250486	1.000000	7.000000	13.000000	21.000000	68.000000
total sulfur dioxide	45.914698	32.782130	6.000000	21.000000	37.000000	61.000000	289.000000
density	0.996730	0.001925	0.990070	0.995570	0.996680	0.997845	1.003690
pH	3.311015	0.156664	2.740000	3.205000	3.310000	3.400000	4.010000
sulphates	0.657708	0.170399	0.330000	0.550000	0.620000	0.730000	2.000000
alcohol	10.442111	1.082196	8.400000	9.500000	10.200000	11.100000	14.900000
quality	5.657043	0.805824	3.000000	5.000000	6.000000	6.000000	8.000000
Id	804.969379	463.997116	0.000000	411.000000	794.000000	1209.500000	1597.000000

특성과 품질의 관계

fig,ax=plt.subplots(6,2,figsize=(15,30))
sns.countplot(x=df.quality,ax=ax[0][0]).set_title('Target Distribution',size=15)
sns.boxplot(x=df.quality,y=df['volatile acidity'],ax=ax[0][1])
sns.boxplot(x=df.quality,y=df['citric acid'],ax=ax[1][0])
sns.boxplot(x=df.quality,y=df['residual sugar'],ax=ax[1][1])
sns.boxplot(x=df.quality,y=df['chlorides'],ax=ax[2][0])
sns.boxplot(x=df.quality,y=df['free sulfur dioxide'],ax=ax[2][1])
sns.boxplot(x=df.quality,y=df['total sulfur dioxide'],ax=ax[3][0])
sns.boxplot(x=df.quality,y=df['density'],ax=ax[3][1])
sns.boxplot(x=df.quality,y=df['pH'],ax=ax[4][0])
sns.boxplot(x=df.quality,y=df['sulphates'],ax=ax[4][1])
sns.boxplot(x=df.quality,y=df['alcohol'],ax=ax[5][0])
sns.boxplot(x=df.quality,y=df['fixed acidity'],ax=ax[5][1])

<AxesSubplot:xlabel='quality', ylabel='fixed acidity'>

상관관계

corr = df.corr()
plt.figure(figsize=(15, 10))
sns.heatmap(corr, annot=True, cmap="Blues", annot_kws={"fontsize":13})
plt.title("Correlation")

Text(0.5, 1.0, 'Correlation')

중요한 와인 특성 pairplot

sns.pairplot(df,corner=True, hue='quality',
            x_vars=['density','alcohol','pH','volatile acidity','citric acid','sulphates','fixed acidity'],
            y_vars=['density','alcohol','pH','volatile acidity','citric acid','sulphates','fixed acidity']
            )

<seaborn.axisgrid.PairGrid at 0x25d96656ee0>

특성 분포

df.hist(figsize=(20,15),bins='auto', color='#6B7FFF')
plt.show()

산점도(전체 이산화황과 자유 이산화황의 관계, 품질)

import plotly.express as px

fig = px.scatter(df, x="total sulfur dioxide", y="free sulfur dioxide", color=df['quality'],  color_continuous_scale='Greens')
fig.update_layout(legend_title_text='Quality')